Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08a291789a7635a6ad7370422f8858b6147ba869de222a42c5a2db199b976829
+oid sha256:fdcf4286bf7155d87f68366b7b66c2a0b30a87f5308541318bf2d72003f913c9
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:125591b31112d0cef25065983364574b0472323383b683b173d665e37180a696
+oid sha256:2601ba1c458b09c41ad2f2fb937bec8965891b6558fb0dababb798678fe7364a
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c900d4c6853d677a7868b2838751ed164390e83255a80643445dc284e68bad62
+oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fc7800513a1b4dd006c457152c700dd768bb49ee4ed8e4d9665a4e42095b054
+oid sha256:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3007518796992481,
+  "epoch": 0.45112781954887216,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 403.055,
       "eval_steps_per_second": 201.528,
       "step": 100
+    },
+    {
+      "epoch": 0.3308270676691729,
+      "grad_norm": 0.0999760627746582,
+      "learning_rate": 9.174206545276677e-05,
+      "loss": 10.3514,
+      "step": 110
+    },
+    {
+      "epoch": 0.3609022556390977,
+      "grad_norm": 0.08799039572477341,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 10.3512,
+      "step": 120
+    },
+    {
+      "epoch": 0.39097744360902253,
+      "grad_norm": 0.13633941113948822,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 10.3508,
+      "step": 130
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.0991743728518486,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 10.3506,
+      "step": 140
+    },
+    {
+      "epoch": 0.45112781954887216,
+      "grad_norm": 0.10438428819179535,
+      "learning_rate": 3.227184283742591e-05,
+      "loss": 10.3492,
+      "step": 150
+    },
+    {
+      "epoch": 0.45112781954887216,
+      "eval_loss": 10.350417137145996,
+      "eval_runtime": 0.3445,
+      "eval_samples_per_second": 406.439,
+      "eval_steps_per_second": 203.219,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1293090816000.0,
+  "total_flos": 1939636224000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null